INDEX

Explanations

Transcription-specific terms

oai_token-act-pair · gpt-3.5-turbo

variations of the word "trans," likely related to transportation or transgender topics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RANT

-0.80

 Sunder

-0.80

mble

-0.75

FontSize

-0.66

 maker

-0.65

FUL

-0.63

 bent

-0.63

 Cage

-0.63

jo

-0.63

awan

-0.61

POSITIVE LOGITS

cend

1.16

gender

1.12

mission

1.11

parency

1.06

mitt

1.06

lator

1.05

missions

1.02

latable

1.02

portation

1.00

lucent

0.99

Activations Density 0.017%

Transcription-specific terms

variations of the word "trans," likely related to transportation or transgender topics

No Comments

No Known Activations